Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3671 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2634. Min Act: -0.0000

Data Index: 658686 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2393. Min Act: -0.0000

Data Index: 263880 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2464. Min Act: -0.0000

Data Index: 804604 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2452. Min Act: -0.0000

Data Index: 751837 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1126604 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1202568 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2348. Min Act: -0.0000

Data Index: 346512 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2203. Min Act: -0.0000

Data Index: 603545 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1085810 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2211. Min Act: -0.0000

Data Index: 681367 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2278. Min Act: -0.0000

Data Index: 65389 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2305. Min Act: -0.0000

Data Index: 761351 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1292987 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1298598 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1263385 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2187. Min Act: -0.0000

Data Index: 317982 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2232. Min Act: -0.0000

Data Index: 533826 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2096. Min Act: -0.0000

Data Index: 459586 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2094. Min Act: -0.0000

Data Index: 548271 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2191. Min Act: -0.0000

Data Index: 921913 (C4 (Web Text))

Max Activating Token Index: 111